© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 5464
    Prev
    Next
    INDEX
    Explanations

    mentions of political figures or specific news events.

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "call"

    np_token-act-pair-logits · gpt-4o-mini

    call, calling

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ChildIndex
    -0.69
    TintMode
    -0.62
    numerusform
    -0.62
    niająca
    -0.61
    ьаж
    -0.60
     MediatR
    -0.60
     négociations
    -0.60
    httphttps
    -0.59
     intégrée
    -0.58
     ferons
    -0.56
    POSITIVE LOGITS
     calling
    1.67
     call
    1.59
     calls
    1.52
    calling
    1.38
     Calling
    1.36
    call
    1.34
    Calling
    1.30
     Call
    1.29
    Call
    1.27
     CALL
    1.22
    Activations Density 2.397%

    No Known Activations